{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2717387676239014, "min": 3.2706680297851562, "max": 3.295699119567871, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 72030.6015625, "min": 21255.86328125, "max": 115515.96875, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 959.6, "min": 436.09090909090907, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19192.0, "min": 16696.0, "max": 23492.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.1142323684549, "min": 1194.3428968907385, "max": 1202.7057443496806, "count": 45 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2396.2284647369097, "min": 2393.110416278334, "max": 16771.890075551113, "count": 45 }, "SoccerTwos.Step.mean": { "value": 499284.0, "min": 9100.0, "max": 499284.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499284.0, "min": 9100.0, "max": 499284.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.009632928296923637, "min": -0.018809394910931587, "max": 0.01007391419261694, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.09632927924394608, "min": -0.29331517219543457, "max": 0.1309608817100525, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.007784527726471424, "min": -0.020163726061582565, "max": -0.0017211500089615583, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.07784527540206909, "min": -0.321410596370697, "max": -0.01721150055527687, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.05684000253677368, "min": -0.5, "max": 0.19935293933924506, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.5684000253677368, "min": -8.0, "max": 3.388999968767166, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.05684000253677368, "min": -0.5, "max": 0.19935293933924506, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.5684000253677368, "min": -8.0, "max": 3.388999968767166, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01252923917490989, "min": 0.009265263719134964, "max": 0.023902750527486204, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01252923917490989, "min": 0.009265263719134964, "max": 0.023902750527486204, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0009007092099636793, "min": 2.652021994435927e-05, "max": 0.004625796945765615, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0009007092099636793, "min": 2.652021994435927e-05, "max": 0.004625796945765615, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0009099281451199204, "min": 2.2246412845561282e-05, "max": 0.004623155016452074, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0009099281451199204, "min": 2.2246412845561282e-05, "max": 0.004623155016452074, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713443452", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/config/poca/SoccerTwos.yaml --env ml-agents/training-env-executables/SoccerTwos.x86_64 --run-id SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713445200" }, "total": 1747.641900863, "count": 1, "self": 0.5623029670000506, "children": { "run_training.setup": { "total": 0.06831463600002508, "count": 1, "self": 0.06831463600002508 }, "TrainerController.start_learning": { "total": 1747.01128326, "count": 1, "self": 1.150616828980219, "children": { "TrainerController._reset_env": { "total": 3.712776445000202, "count": 3, "self": 3.712776445000202 }, "TrainerController.advance": { "total": 1741.85666664102, "count": 32834, "self": 1.3255909720230648, "children": { "env_step": { "total": 1100.9859284589975, "count": 32834, "self": 891.0796303019877, "children": { "SubprocessEnvManager._take_step": { "total": 209.1213839550187, "count": 32834, "self": 7.866984353005762, "children": { "TorchPolicy.evaluate": { "total": 201.25439960201294, "count": 65238, "self": 201.25439960201294 } } }, "workers": { "total": 0.7849142019910573, "count": 32834, "self": 0.0, "children": { "worker_root": { "total": 1742.4318820689796, "count": 32834, "is_parallel": true, "self": 1011.4445486370073, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00716412299999547, "count": 2, "is_parallel": true, "self": 0.004172961999984182, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029911610000112887, "count": 8, "is_parallel": true, "self": 0.0029911610000112887 } } }, "UnityEnvironment.step": { "total": 0.05136752800001432, "count": 1, "is_parallel": true, "self": 0.001393323999934637, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009983710000369683, "count": 1, "is_parallel": true, "self": 0.0009983710000369683 }, "communicator.exchange": { "total": 0.044745535999993535, "count": 1, "is_parallel": true, "self": 0.044745535999993535 }, "steps_from_proto": { "total": 0.004230297000049177, "count": 2, "is_parallel": true, "self": 0.000737669000045571, "children": { "_process_rank_one_or_two_observation": { "total": 0.003492628000003606, "count": 8, "is_parallel": true, "self": 0.003492628000003606 } } } } } } }, "UnityEnvironment.step": { "total": 730.9823270119725, "count": 32833, "is_parallel": true, "self": 46.991319441982, "children": { "UnityEnvironment._generate_step_input": { "total": 28.60093899799483, "count": 32833, "is_parallel": true, "self": 28.60093899799483 }, "communicator.exchange": { "total": 512.1773981309882, "count": 32833, "is_parallel": true, "self": 512.1773981309882 }, "steps_from_proto": { "total": 143.2126704410075, "count": 65666, "is_parallel": true, "self": 25.112212906075058, "children": { "_process_rank_one_or_two_observation": { "total": 118.10045753493245, "count": 262664, "is_parallel": true, "self": 118.10045753493245 } } } } }, "steps_from_proto": { "total": 0.005006419999745049, "count": 4, "is_parallel": true, "self": 0.001064964999386575, "children": { "_process_rank_one_or_two_observation": { "total": 0.003941455000358474, "count": 16, "is_parallel": true, "self": 0.003941455000358474 } } } } } } } } }, "trainer_advance": { "total": 639.5451472099995, "count": 32834, "self": 9.06511179998256, "children": { "process_trajectory": { "total": 189.13191706501658, "count": 32834, "self": 188.8667908120163, "children": { "RLTrainer._checkpoint": { "total": 0.2651262530002896, "count": 1, "self": 0.2651262530002896 } } }, "_update_policy": { "total": 441.3481183450004, "count": 23, "self": 35.52136787600023, "children": { "TorchPOCAOptimizer.update": { "total": 405.82675046900016, "count": 230, "self": 405.82675046900016 } } } } } } }, "trainer_threads": { "total": 1.0339999789721332e-06, "count": 1, "self": 1.0339999789721332e-06 }, "TrainerController._save_models": { "total": 0.2912223109997285, "count": 1, "self": 0.00551674699954674, "children": { "RLTrainer._checkpoint": { "total": 0.28570556400018177, "count": 1, "self": 0.28570556400018177 } } } } } } }